Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

timestamp masking

Timestamp masking is a data augmentation and regularization technique in time series machine learning where specific time steps or their latent feature representations within a temporal sequence are randomly hidden or set to zero during training. By altering the context while preserving overall sequence alignment, this technique generates diverse views that encourage neural networks to infer missing information from surrounding observations and learn robust temporal dependencies. It is commonly applied in self-supervised and contrastive learning frameworks to prevent overfitting to raw observation values and to facilitate fine-grained representation learning for downstream tasks such as forecasting, classification, and anomaly detection.

1 item

TS2Vec: Towards Universal Representation of Time Series

TS2Vec: Towards Universal Representation of Time Series

Zhihan Yue, Yujing Wang, Juanyong Duan, Tianmeng Yang, Congrui Huang, Yunhai Tong, Bixiong Xu

OrganizationsMicrosoftPeking University

Why you should read this

Proposes a universal contrastive learning framework that uses hierarchical contrasting and contextual consistency to learn multiscale time series representations, achieving state-of-the-art results across classification, forecasting, and anomaly detection benchmarks.

This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp. Furthermore, to obtain the representation of an arbitrary sub-sequence in the time series, we can apply a simple aggregation over the representations of corresponding timestamps. We conduct extensive experiments on time series classification tasks to evaluate the quality of time series representations. As a result, TS2Vec achieves significant improvement over existing SOTAs of unsupervised time series representation on 125 UCR datasets and 29 UEA datasets. The learned timestamp-level representations also achieve superior results in time series forecasting and anomaly detection tasks. A linear regression trained on top of the learned representations outperforms previous SOTAs of time series forecasting. Furthermore, we present a simple way to apply the learned representations for unsupervised anomaly detection, which establishes SOTA results in the literature. The source code is publicly available at https://github.com/yuezhihan/ts2vec.

Added

2026-09-26